(基于文件) 日志存储

Optuna 提供了 JournalStorage。通过此功能，您可以使用 NFS 作为共享存储，轻松地在网络上进行分布式优化，而无需设置 RDB 或 Redis。

import logging
import sys

import optuna


# Add stream handler of stdout to show the messages
optuna.logging.get_logger("optuna").addHandler(logging.StreamHandler(sys.stdout))
study_name = "example-study"  # Unique identifier of the study.
file_path = "./optuna_journal_storage.log"
storage = optuna.storages.JournalStorage(
    optuna.storages.journal.JournalFileBackend(file_path),  # NFS path for distributed optimization
)

study = optuna.create_study(study_name=study_name, storage=storage)


def objective(trial):
    x = trial.suggest_float("x", -10, 10)
    return (x - 2) ** 2


study.optimize(objective, n_trials=3)

A new study created in Journal with name: example-study
Trial 0 finished with value: 4.596235497552234 and parameters: {'x': -0.1438832751696708}. Best is trial 0 with value: 4.596235497552234.
Trial 1 finished with value: 18.936178621670795 and parameters: {'x': 6.3515719713306815}. Best is trial 0 with value: 4.596235497552234.
Trial 2 finished with value: 24.768028479300177 and parameters: {'x': -2.976748786034933}. Best is trial 0 with value: 4.596235497552234.

尽管此示例中的优化时间太短，无法并行运行，但您可以扩展此示例来编写一个可以并行运行的优化脚本。

注意

在 Windows 环境中，可能会出现“客户端未拥有必需的特权”的错误消息。在这种情况下，您可以通过指定 JournalFileOpenLock 来创建存储，从而解决问题。有关详细信息，请参阅 JournalStorage 的参考。